Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92727
    Prev
    Next
    INDEX
    Explanations

    mathematical or structural representations involving brackets or fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.85
    expandindo
    -0.77
     indígen
    -0.75
    ientras
    -0.74
    transQ
    -0.73
    RectangleBorder
    -0.71
     AssemblyCompany
    -0.71
     increí
    -0.70
    ChildScrollView
    -0.70
    WithMany
    -0.69
    POSITIVE LOGITS
    
    0.31
    jdbc
    0.30
    ">//
    0.28
     Fla
    0.28
     LC
    0.26
     nitro
    0.25
     تانيه
    0.25
     
    0.25
     
    0.25
     dar
    0.24
    Activations Density 0.000%

    No Known Activations